Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4916 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4286. Min Range: -6.4286
Max Act: 6.4286. Min Act: -0.1700
Data Index: 1726620 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4286. Min Range: -6.4286
Max Act: 6.3348. Min Act: -0.1700
Data Index: 1323449 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4286. Min Range: -6.4286
Max Act: 6.3036. Min Act: -0.1700
Data Index: 5770857 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4286. Min Range: -6.4286
Max Act: 6.2411. Min Act: -0.1700
Data Index: 2899701 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4286. Min Range: -6.4286
Max Act: 6.1786. Min Act: -0.1700
Data Index: 7892451 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4286. Min Range: -6.4286
Max Act: 6.1786. Min Act: -0.1700
Data Index: 2249409 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4286. Min Range: -6.4286
Max Act: 6.1473. Min Act: -0.1700
Data Index: 8398313 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4286. Min Range: -6.4286
Max Act: 6.1161. Min Act: -0.1700
Data Index: 6227391 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4286. Min Range: -6.4286
Max Act: 6.0536. Min Act: -0.1700
Data Index: 6469572 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4286. Min Range: -6.4286
Max Act: 6.0536. Min Act: -0.1700
Data Index: 1491502 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4286. Min Range: -6.4286
Max Act: 6.0536. Min Act: -0.1700
Data Index: 7190718 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4286. Min Range: -6.4286
Max Act: 6.0536. Min Act: -0.1700
Data Index: 264927 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4286. Min Range: -6.4286
Max Act: 6.0223. Min Act: -0.1700
Data Index: 2290002 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4286. Min Range: -6.4286
Max Act: 6.0223. Min Act: -0.1700
Data Index: 6829350 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4286. Min Range: -6.4286
Max Act: 5.9911. Min Act: -0.1700
Data Index: 1758833 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4286. Min Range: -6.4286
Max Act: 5.9598. Min Act: -0.1700
Data Index: 1768224 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4286. Min Range: -6.4286
Max Act: 5.9598. Min Act: -0.1700
Data Index: 3303742 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4286. Min Range: -6.4286
Max Act: 5.9286. Min Act: -0.1700
Data Index: 7960963 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4286. Min Range: -6.4286
Max Act: 5.8973. Min Act: -0.1700
Data Index: 7740287 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4286. Min Range: -6.4286
Max Act: 5.8973. Min Act: -0.1700
Data Index: 3464838 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19